https://doi.org/10.4081/jae.2026.2003
Real-time banana harvest readiness prediction using mobile SE-enhanced YOLO classification
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Published: 28 January 2026
A digital banana harvesting solution was developed to improve the speed and consistency of banana harvesting by integrating real-time bunch detection with harvest-readiness classification into a mobile decision support system used directly in the field. The banana bunch detection module utilizes a You Only Look Once (YOLO) model trained on a custom dataset collected under real plantation conditions, enabling consistent performance across varied environments. Specifically, a YOLOv12n detector was used for banana bunch detection, achieving 93% AP50-test with an inference latency of 5.1 ms per image, making it suitable for mobile deployment in plantation environments. For the readiness of harvesting prediction, a second model was developed, based on a squeeze-and-excitation YOLO classifier, using annotated images gathered with guidance from harvesting experts. In this work, this SE-enhanced YOLO classifier is used as a lightweight, task-specific YOLO classification backbone for the binary “cut” vs “keep” decision, and this harvest-readiness classifier achieved 94% accuracy with an inference time of 2.8 ms per image. Then, an application was built using Flutter and Dart, which uses intuitive interfaces for both field operators and administrators, and includes integrated feedback mechanisms to collect user input and support continuous model refinement. Field testing across diverse lighting and environmental conditions, as well as usability assessments with expert harvesters and administrative staff, demonstrated reliable performance with potential to contribute to faster decision-making and reduced manual labour.
Downloads
Altaf S, Ahmad S, Zaindin M, Soomro MW, 2020. Xbee-based WSN architecture for monitoring of banana ripening process using knowledge-level artificial intelligent technique. Sensors (Basel) 20:4033. DOI: https://doi.org/10.3390/s20144033
Bac CW, Van Henten EJ, Hemming J, Edan Y, 2014. Harvesting robots for high-value crops: state-of-the-art review and challenges ahead. J Field Robot 31: 888-911. DOI: https://doi.org/10.1002/rob.21525
Baglat P, Hayat A, Mostafa SS, Mendonça F, Morgado Dias F, 2025a. Banana bunch dataset: multi-field acquisition with various environmental conditions. Available from: https://zenodo.org/records/15642838
Baglat P, Hayat A, Mostafa SS, Mendonça F, Morgado-Dias F, 2025b. Comparative analysis and evaluation of YOLO generations for banana bunch detection. Smart Agr Technol 12:101100. DOI: https://doi.org/10.1016/j.atech.2025.101100
Chuquimarca L, Vintimilla B, Velastin S, 2023. Banana ripeness level classification using a simple CNN model trained with real and synthetic datasets. Proc. 18th Int. Conf. Computer Vision Theory and Applications (VISAPP). Lisbon; pp. 536-543. DOI: https://doi.org/10.5220/0011654600003417
Dadzie BK, Orchard JE, 1997. Routine post-harvest screening of banana/plantain hybrids: criteria and methods. Accessed: 12 October 2025. Available from: https://cgspace.cgiar.org/bitstreams/295b5ef7-3a0f-4f6c-bec3-661330300f40/download
Dai G, Tian Z, Fan J, Sunil CK, Dewi C, 2024. DFN-PSAN: Multi-level deep information feature fusion extraction network for interpretable plant disease classification. Comput Electron Agric 216:108481. DOI: https://doi.org/10.1016/j.compag.2023.108481
Dewi C, Mahmudy WF, Arisoesilaningsih E, Solimun S, 2021. Review of non-destructive banana ripeness identification using imagery data. Proc. 6th Int. Conf. Sustainable Information Engineering and Technology, Malang; pp. 348-354. DOI: https://doi.org/10.1145/3479645.3479685
Ergün E, 2025. High precision banana variety identification using vision transformer based feature extraction and support vector machine. Sci Rep 15:10366. DOI: https://doi.org/10.1038/s41598-025-95466-0
FAO, WHO, 2022. Standard for bananas (CXS 205-1997): 2022 amendment. Accessed: 22 July 2025. Available from: https://www.fao.org/fao-who-codexalimentarius/codex-texts/list-standards/en/
Ferdaus MH, Prito RH, Rasel AAS, Ahmed M, Saykot MJH, Shanta SS, et al., 2025. BananaImageBD: A comprehensive banana image dataset for classification of banana varieties and detection of ripeness stages in Bangladesh. Data Brief 58:111239. DOI: https://doi.org/10.1016/j.dib.2024.111239
Fu L, Duan J, Zou X, Lin G, Song S, Ji B, Yang Z, 2019. Banana detection based on color and texture features in the natural environment. Comput. Electron. Agric. 167:105057. DOI: https://doi.org/10.1016/j.compag.2019.105057
Fu L, Duan J, Zou X, Lin J, Zhao L, Li J, Yang Z, 2020. Fast and accurate detection of banana fruits in complex background orchards. IEEE Access 8:196835-196846. DOI: https://doi.org/10.1109/ACCESS.2020.3029215
Fu L, Wu F, Zou X, Jiang Y, Lin J, Yang Z, Duan J, 2022a. Fast detection of banana bunches and stalks in the natural environment based on deep learning. Comput Electron Agric 194:106800. DOI: https://doi.org/10.1016/j.compag.2022.106800
Fu L, Yang Z, Wu F, Zou X, Lin J, Cao Y, Duan J, 2022b. YOLO-Banana: a lightweight neural network for rapid detection of banana bunches and stalks in the natural environment. Agronomy 12:391. DOI: https://doi.org/10.3390/agronomy12020391
Hayat A, Baglat P, Mendonça F, Mostafa SS, Dias FM, Garces H, 2023. Banana bunch harvesting dataset. Mendeley Data, V1. Available from: https://data.mendeley.com/datasets/kjrsb7ztr9/1
Hayat A, Baglat P, Mendonça F, Mostafa SS, Morgado-Dias F, 2024. Machine learning system for commercial banana harvesting. Eng Res Express 6:035202. DOI: https://doi.org/10.1088/2631-8695/ad5cd2
Hu J, Shen L, Albanie S, Sun G, Wu E, 2018. Squeeze-and-excitation networks. IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City; pp. 7132-7141. DOI: https://doi.org/10.1109/CVPR.2018.00745
Knott M, Perez-Cruz F, Defraeye T, 2023. Facilitated machine learning for image-based fruit quality assessment. J Food Eng 345:111401. DOI: https://doi.org/10.1016/j.jfoodeng.2022.111401
Ni J, Gao J, Deng L, Han Z, 2020. Monitoring the change process of banana freshness by GoogLeNet. IEEE Access 8:228369-228376. DOI: https://doi.org/10.1109/ACCESS.2020.3045394
Piedad E, Larada JI, Pojas GJ, Ferrer LVV, 2018. Postharvest classification of banana (Musa acuminata) using tier-based machine learning. Postharvest Biol Technol 145:93-100. DOI: https://doi.org/10.1016/j.postharvbio.2018.06.004
Sa I, Ge Z, Dayoub F, Upcroft B, Perez T, McCool C, 2016. Deepfruits: A fruit detection system using deep neural networks. Sensors (Basel) 16:1222. DOI: https://doi.org/10.3390/s16081222
Wang G, Gao Y, Xu F, Sang W, Han Y, Liu Q, 2025. A banana ripeness detection model based on improved YOLOv9c multifactor complex scenarios. Symmetry 17:231. DOI: https://doi.org/10.3390/sym17020231
Wu F, Duan J, Chen S, Ye Y, Ai P, Yang Z, 2021. Multi-target recognition of bananas and automatic positioning for the inflorescence axis cutting point. Front Plant Sci 12:705021. DOI: https://doi.org/10.3389/fpls.2021.705021
Zhang R, Li X, Zhu L, Zhong M, Gao Y, 2021. Target detection of banana string and fruit stalk based on YOLOv3 deep learning network. Proc. IEEE 2nd Int. Conf. on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Nanchang; pp. 346-349. DOI: https://doi.org/10.1109/ICBAIE52039.2021.9389948
Zhang Y, Lian J, Fan M, Zheng Y, 2018. Deep indicator for fine-grained classification of banana’s ripening stages. EURASIP J Image Video Process 2018:46. DOI: https://doi.org/10.1186/s13640-018-0284-8
CRediT authorship contribution
Preety Baglat, investigation, writing-original draft preparation and incorporation of revisions, methodology, and app development; Preety Baglat, Sidharth Gupta, review/validation, editing, and app development; Francisco Silva, Helena Garcês, Ruben Sousa, Diana Côrte, review, industry collaboration, field management support, and operational feedback; Fábio Mendonça, Sheikh Shanawaz Mostafa, Fernando Morgado-Dias, supervision, review/validation, and editing, All authors read and approved the final version of the manuscript and agreed to be accountable for all aspects of the work.
Supporting Agencies
Data Availability Statement
The dataset used in this study will be made publicly available on Mendeley for banana bunch harvesting (Hayat et al., 2023) and Zenodo for bunch detection (Baglat et al., 2025a). The questionnaire instrument is included in the Supplementary File; GESBA holds raw questionnaire responses and may be shared upon reasonable request and with their permission.
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.